Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 5761
    Prev
    Next
    INDEX
    Explanations

    references to adaptations based on works from various mediums

    oai_token-act-pair · gpt-3.5-turbo

    references to adaptations or inspirations of films from other media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]=>
    -0.78
    displayText
    -0.70
    =(
    -0.68
    sudo
    -0.66
    ]=
    -0.65
    ertodd
    -0.65
    Justice
    -0.64
     unchecked
    -0.64
    needed
    -0.63
    alone
    -0.62
    POSITIVE LOGITS
     themes
    0.78
     illustrations
    0.75
     conventions
    0.75
     philosophies
    0.72
     theme
    0.72
     ideals
    0.71
     playbook
    0.71
     motif
    0.71
    Ö¼
    0.70
     sketches
    0.70
    Activations Density 0.669%

    No Known Activations